• 디지털산업정보학회논문지
• /
• 제14권4호
• /
• pp.69-77
• /
• 2018

The malignant melanoma accounts for about 1 to 3% of the total malignant tumor in the West, especially in the US, it is a disease that causes more than 9,000 deaths each year. Generally, skin lesions are difficult to detect the features through photography. In this paper, we propose a computer-aided diagnosis algorithm based on deep learning for classification of malignant melanoma and benign skin tumor in RGB channel skin images. The proposed deep learning model configures the tumor lesion segmentation model and a classification model of malignant melanoma. First, U-Net was used to segment a skin lesion area in the dermoscopic image. We could implement algorithms to classify malignant melanoma and benign tumor using skin lesion image and results of expert's labeling in ResNet. The U-Net model obtained a dice similarity coefficient of 83.45% compared with results of expert's labeling. The classification accuracy of malignant melanoma obtained the 83.06%. As the result, it is expected that the proposed artificial intelligence algorithm will utilize as a computer-aided diagnosis algorithm and help to detect malignant melanoma at an early stage.

• 한국지반공학회지:지반
• /
• 제14권2호
• /
• pp.107-126
• /
• 1998

터널굴착으로 발생되는 지반침하는 지상구조물의 변형을 유발할 수도 있으므로 터널굴착 전에 지상구조물의 안전성 평가가 요구된다. 이러한 변형에 대한 구조물의 안전성을 평가하기 위하여 본 연구에서는 터널현장의 지반침하를 예측하고, 이를 기반으로 지상구조물의 안정성 평가를 수행하는 전문가 시스템 NESASS(Neural Network Expert System for Adjacent Structure Safety analysis)를 개발하였다. NESASS는 인공신경망을 이용, 터널현장의 지반침하 계측자료로 작성된 데이터베이스 자료를 학습자료로 하여 학습을 수행하고, 이를 기반으로 터널현장의 지반침하 트라프를 추론한다. 또한 일반구조물의 안전성을 평가하는데 이용되고 있는 인자, 즉 각변형(angular distortion)과 처징비 (deflection ratio) 등을 이용하여 지상건물의 안전성을 평가함과 아울러 Dulacska의 균열평가 모델 을 이용하여 건물의 균열양상을 예측한다. 본 연구에서는 서울지하철 현장을 대상으로 113개 계측측선의 지반침하 계측자료를 수집 정리하고 지반침하의 주 영향인자들을 선정하여. 이들을 데이터베이스화하였다. 그리고 인공신경망 구조에 관련된 매개변수 연구를 수행하여 구축된 데이터베이스에 대한 최적 인공신경망 모델을 선정하였다. 또한 현장자료와의 비교를 통하여 NESASS의 지반침하 예측능력을 조사하고, 현장자료를 이용하여 지상구조물에 대한 안전성 평가의 신뢰성을 평가함으로써 NESASS의 실무 적용성을 확인 하였다.

• 한국원자력학회:학술대회논문집
• /
• 한국원자력학회 2005년도 춘계학술발표회
• /
• pp.1261-1262
• /
• 2005

• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 2002년도 춘계학술대회 논문집
• /
• pp.201-202
• /
• 2002

No Abstract(See Full Text)

• Educational Technology International
• /
• 제11권2호
• /
• pp.77-103
• /
• 2010

The purpose of this study was to develop an instructional model using new technologies aiming to secure students' learnability and to enhance the public school values in the rural districts. The present study attempts to suggest a practical e-learning instructional and learning model named Group Dynamics- based Debate Instructional Model', which utilizes unique technology environment conditions in most. To develop the model, concepts of group dynamics and debate-based instructional models were reviewed. And in-service teachers in two public schools in a certain rural district were interviewed in order to collect and analyze their needs for a teaching and learning model with which they utilizes unique technology conditions as environment in most. Based on literature review and the need analysis, a group dynamics-based debate instructional model has been suggested in terms of conceptual model. And then expert assessment composing of five in-service teachers from the model schools was implemented twice in order to acquire the suggested model validation, followed by the model validation by a group of experts. Then a revised group dynamics-based debate instructional model has been finally suggested. The group dynamics-based debate instructional model is expected to build up members' affective connection in the process, to generate group value, or collective intelligence, and to establish positive discussion culture. Furthermore, beyond of just utilizing the existing materials, learners are encouraged to develop and collect their own materials and data such as expert's interview, or public news for their argument or refutation. In doing so, learners enhance their learnability as well as accountability, prompting self-directed learning, and establishing appropriate discussion culture resulting in positive learning outcomes.

• 한국의학물리학회지:의학물리
• /
• 제30권4호
• /
• pp.94-103
• /
• 2019

Purpose: To evaluate the clinical feasibility of knowledge-based planning (KBP) for volumetric-modulated arc radiotherapy (VMAT) in spine stereotactic body radiotherapy (SBRT). Methods: Forty-eight VMAT plans for spine SBRT was studied. Two planning target volumes (PTVs) were defined for simultaneous integrated boost: PTV for boost (PTV-B: 27 Gy/3fractions) and PTV elective (PTV-E: 24 Gy/3fractions). The expert VMAT plans were manually generated by experienced planners. Twenty-six plans were used to train the KBP model using Varian RapidPlan. With the trained KBP model each KBP plan was automatically generated by an individual with little experience and compared with the expert plan (closed-loop validation). Twenty-two plans that had not been used for KBP model training were also compared with the KBP results (open-loop validation). Results: Although the minimal dose of PTV-B and PTV-E was lower and the maximal dose was higher than those of the expert plan, the difference was no larger than 0.7 Gy. In the closed-loop validation, D_1.2cc, D_0.35cc, and D_mean of the spinal cord was decreased by 0.9 Gy, 0.6 Gy, and 0.9 Gy, respectively, in the KBP plans (P<0.05). In the open-loop validation, only D_mean of the spinal cord was significantly decreased, by 0.5 Gy (P<0.05). Conclusions: The dose coverage and uniformity for PTV was slightly worse in the KBP for spine SBRT while the dose to the spinal cord was reduced, but the differences were small. Thus, inexperienced planners could easily generate a clinically feasible plan for spine SBRT by using KBP.

• 제어로봇시스템학회논문지
• /
• 제13권8호
• /
• pp.726-734
• /
• 2007

Generally, a mobile robot is moved by original input programs. However, it is very hard for a non-expert to change the program generating the moving path of a mobile robot, because he doesn't know almost the teaching command and operating method for driving the robot. Therefore, the teaching method with speech command for a handicapped person without hands or a non-expert without an expert knowledge to generate the path is required gradually. In this study, for easily teaching the moving path of the autonomous mobile robot, the autonomous mobile robot with the function of speech recognition is developed. The use of human voice as the teaching method provides more convenient user-interface for mobile robot. To implement the teaching function, the designed robot system is composed of three separated control modules, which are speech preprocessing module, DC servo motor control module, and main control module. In this study, we design and implement a speaker dependent isolated word recognition system for creating moving path of an autonomous mobile robot in the unknown environment. The system uses word-level Hidden Markov Models(HMM) for designated command vocabularies to control a mobile robot, and it has postprocessing by neural network according to the condition based on confidence score. As the spectral analysis method, we use a filter-bank analysis model to extract of features of the voice. The proposed word recognition system is tested using 33 Korean words for control of the mobile robot navigation, and we also evaluate the performance of navigation of a mobile robot using only voice command.

• 한국지능시스템학회논문지
• /
• 제1권1호
• /
• pp.9-25
• /
• 1991

This tutorial paper has been written for biologists, physicians or beginners in fuzzy sets theory and applications. This field is introduced in the framework of medical diagnosis problems. The paper describes and illustrates with practical examples, a general methodology of special interest in the processing of borderline cases, that allows a graded assignment of diagnoses to patients. A pattern of medical knowledge consists of a tableau with linguistic entries or of fuzzy propositions. Relationships between symptoms and diagnoses are interpreted as labels of fuzzy sets. It is shown how possibility measures (soft matching) can be used and combined to derive diagnoses after measurements on collected data. The concepts and methods are illustrated in a biomedical application on inflammatory protein variations. In the case of poor diagnostic classifications, it is introduced appropriate ponderations, acting on the characterizations of proteins, in order to decrease their relative influence. As a consequence, when pattern matching is achieved, the final ranking of inflammatory syndromes assigned to a given patient might change to better fit the actual classification. Defuzzification of results (i.e. diagnostic groups assigned to patients) is performed as a non fuzzy sets partition issued from a "separating power", and not as the center of gravity method commonly employed in fuzzy control. It is then introduced a model of fuzzy connectionist expert system, in which an artificial neural network is designed to build the knowledge base of an expert system, from training examples (this model can also be used for specifications of rules in fuzzy logic control). Two types of weights are associated with the connections: primary linguistic weights, interpreted as labels of fuzzy sets, and secondary numerical weights. Cell activation is computed through MIN-MAX fuzzy equations of the weights. Learning consists in finding the (numerical) weights and the network topology. This feed forward network is described and illustrated in the same biomedical domain as in the first part.

• 한국조경학회지
• /
• 제30권3호
• /
• pp.1-11
• /
• 2002

The purpose of this study is to construct an evaluation criteria based on the relative importance and various combinations of each evaluation index and then to appraise urban biotope in terms of nature experience and recreation. After the standard of evaluation had been developed through the review of existing literature, the relative importance of the evaluation index through expert survey was determined, and the evaluation model to assess biotope value was established. The results of this study are as follows; 1) We have constructed the seventeen evaluation criteria through literature reviews, and have provided relative importance to each evaluation index of the natural in biotope, the diversity of landscape patterns, the appearance-existence of water space, the special landscape elements, and the access based on the results of expert survey. and then we have constructed an evaluation system using the relative importance criteria. 2) To evaluate urban biotope using the evaluation system constructed, we selected 14 sites. The final evaluation results of each site is as follows; The first grade areas are the water space with semi-natural style in front of Gangchon Woobang apartments, the forest zone near Page Temple at Mt. Palgong, the edge area of Jisan and Gosan and the tendril yard against Anshim middle school. The second grade areas are Hyomyung elementary school, the farm land behind the third Anshim Jugong apartment, Ehyun put and the swampy land in front of the Kangchon and Anshim construction site. The third grade areas are Seohan and Hwasung high-rise apartments at Beummul-Dong, the Korea Manpower Agency in the Sungseo industrial zone, and the adjacent area of St. Tongil. The only fourth grade area is the commercial zone near Taegu Department Store. 3) It is highly useful to evaluate urban biotope using the evaluation criteria constructed for this research, the evaluation criteria we developed may be difficult to encompass all expert opinion and the period of space-formation is difficult to estimate urban biotopes. In the future, it is necessary to gather the basic data suitable to estimate biotope and it is necessary to develop detailed evaluation criteria applicable to estimate every biotope that has specific property.

• 한국환경복원기술학회지
• /
• 제13권5호
• /
• pp.59-80
• /
• 2010

This research This research aims at developing systemic evaluation model in terms of biotope preservation through reports, literatures, and expert survey analysis by implementing biotope structure analysis in area level with selecting Hyunpoong and Yuga-myeon, Dalseong county, Daegu metropolitan city as a site. First of all, as a result of biotope type classification of research site, biotope type groups are classified into total 13, and its biotope types are divided into total 61. Also, as a result of literature analysis, total 18 items are drawn such as diversity of biotope typical species as a index item to assess the preservation value of biotope, and the first evaluation index are divided into 10 and the second ones are divided into 8 according to characteristic of index items. As a result of expert survey analysis, All 10 index items, first evaluation index, show high importance average (above 4.7). As a result of implementation of main cause for categorizing evaluation index by characteristic, there are 3 factors such as 'obstructive factor.' Based on above survey analysis result, as a result of estimating the weight of each item, 'restoration factor' showed the highest, 3.4541, but 'factor of habitat stability' showed 3.1468, which is the lowest The systemic value evaluation was set by comprehensively analyzing these results. As a result of biotope preservation value evaluation through applying research site, total 19 types which are abundant in vegetation are classified into I class, 12 types in II class, 5 types in III class, 10 types in IV class, and 15 types in V class respectively. Lastly, as a result of second evaluation, it is analyzed that there are 17 special meaningful space to preserve species and biotope(1a, 1b) and 61 meaningful space to preserve species (2a, 2b, 2c).